easy-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@easy-mcpconvert my Python functions into MCP tools for Claude"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
easy-mcp ⚡🤖
Ultra-lightweight, zero-dependency Python framework for Model Context Protocol (MCP). Build MCP servers for Claude in seconds.
Turn standard Python functions into Model Context Protocol tools for Claude Desktop and Claude Code with simple @mcp.tool() decorators.
⚡ Why easy-mcp?
Zero dependencies: Written in 100% pure standard Python. No heavy ASGI servers, no complex async overhead.
Pythonic & Simple: Turn any Python function into an MCP tool with a single decorator
@mcp.tool().Automatic Schema Inspection: Docstrings and type annotations are automatically converted into standard JSON Schemas.
Claude Desktop Ready: Built-in config generator outputs the exact JSON configuration to paste into
claude_desktop_config.json.Offline & Safe: Standard I/O (stdio) JSON-RPC 2.0 communication.
Related MCP server: MCP Python Server — API Wrapper
📦 Installation
pip install easy-mcp🚀 30-Second Quickstart
1. Write your server (my_tools.py)
from easy_mcp import EasyMCP
mcp = EasyMCP(name="my-tools", version="1.0.0")
@mcp.tool()
def add(a: float, b: float) -> float:
"""Add two numbers together.
Args:
a: First number
b: Second number
"""
return a + b
@mcp.tool()
def get_system_info() -> dict:
"""Get basic platform system information."""
import platform
return {
"system": platform.system(),
"release": platform.release(),
"machine": platform.machine()
}
if __name__ == "__main__":
mcp.run()2. Add to Claude Desktop
Generate the configuration snippet:
easy-mcp config my_tools.pyOutput:
{
"mcpServers": {
"my-tools": {
"command": "python",
"args": [
"E:\\opensource\\my_tools.py"
]
}
}
}Paste this into your claude_desktop_config.json:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
Restart Claude Desktop, and your tools will appear with the 🔨 hammer icon!
🛠️ CLI Utilities
Scaffold a new server in 1 second:
easy-mcp init weather-serverGenerate config for Claude Desktop:
easy-mcp config server.py📂 Community MCP Examples (Help Wanted!)
We are building a curated collection of lightweight MCP tool servers in examples/:
examples/basic_math.py- Math calculatorexamples/pii_shield_mcp.py- AI data privacy sanitizer
Want to contribute?
Help us add more examples:
🌐 SQLite database query tool
📰 Hacker News API reader
📁 Local markdown note searcher
⛅ Weather lookup
See CONTRIBUTING.md to submit an example!
📄 License
MIT License © 2026 lui01212
This server cannot be deployed
Maintenance
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Research-backed linting + generation for agent context files (CLAUDE.md, AGENTS.md, Cursor rules).
Build, validate, deploy — HTTP APIs, cron jobs, webhooks and MCP tools — from your AI client.
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
Related MCP Servers
- AlicenseDqualityDmaintenanceA foundation for building custom local Model Context Protocol (MCP) servers that provide tools accessible to AI assistants like Cursor or Claude Desktop.137MIT
- FlicenseNot gradedqualityDmaintenanceA Python server implementing the Model Context Protocol that exposes tools for querying external APIs, compatible with Claude Desktop and ChatGPT Desktop.-
- AlicenseNot gradedqualityDmaintenanceA universal framework for creating and deploying custom Model Context Protocol (MCP) tool servers with decorator-based tool registration, supporting multiple transports and automatic JSON schema generation for AI assistants.1MIT
- AlicenseNot gradedqualityCmaintenanceEnables standardized interactions between LLMs and CMMV applications using the Model Context Protocol, with decorator-based tool registration and flexible transport options.3 npmMIT